Triple
T3822139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tax Cuts and Jobs Act of 2017 |
E88596
|
entity |
| Predicate | corporateTaxRateAfter |
P37503
|
FINISHED |
| Object | 21 percent |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 21 percent | Statement: [Tax Cuts and Jobs Act of 2017, corporateTaxRateAfter, 21 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: corporateTaxRateAfter Context triple: [Tax Cuts and Jobs Act of 2017, corporateTaxRateAfter, 21 percent]
-
A.
topCorporateRateAfterReform
chosen
Indicates the highest corporate tax rate that applies following the implementation of a specified tax reform.
-
B.
topCorporateRateBeforeReform
Indicates the highest corporate tax rate that was in effect prior to a specified tax reform or policy change.
-
C.
taxationMethod
Indicates the specific way or system by which taxes are calculated, collected, or applied in a given context.
-
D.
taxFunction
Indicates the rule or calculation method used to determine the amount of tax applied to a given input (such as income, price, or transaction).
-
E.
taxType
Indicates the specific category or classification of tax that applies to an entity, transaction, or amount.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69aed9538cf881909d9ce8ca4ac7c18c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef188b474819087680db42b04ecdd |
completed | March 9, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69aee74a2bc081909b237df8b1e27653 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:17 p.m.